You are on page 1of 8
the problem as “There are too few servers,” “There aren't enough tables,” or “The servers need to work faster.” The real problem was identified correctly as "The customers must ‘wait too long.” ‘Another concept that has been difficult for study teams 's localization, which is a process of focusing on smaller and smaller vital pieces of the problem. This concept initally proved difficult because team members had not yet internal lized the idea that improvement should be driven by customer requirements Some study teams have experienced an assortment of ‘other cificultes. Occasionally, team members could not see the benefit of collecting data accurately, or they did not under stand how baseline data would be used to validate a solu tion. Some members had trouble keeping an open mind and, consequently, resisted investigating the effects of variables Chapter 8 Process Improvement 203, they felt to be lrelevant. n some cases, members had to learn ‘new kil, such as how to obtain information in a nonthreat- ening way from workers in the system. Finally, organizational problems such as arranging meeting times and getting sup- port from co-workers had to be resolved as well Questions 1, How is SSM alferent from Deming’s PDCA cycle? 2. Prepare a cause-and-effect or shbone dlagram for aproblem such as “Why customers have long waits for coffee.” Your fishbone diagram should be similar to that in Figure 8.17, Using the main sources of cause: policy, procedure, people, and physical environment. 3. How would you resolve the dificulies that study teams have experienced when applying SSM? ros Data Envelopment Analysis (DEA) How can corporate management evaluate the productivity of a fast-food outlet, a branch, bank, a health clinic, or an elementary school? The difficulties in measuring productivity are threefold, First, what are the appropriate inputs to the system (e.g, labor hours, mate- rial dollars) and the measures of those inputs? Second, what are the appropriate outputs, of the system (e.g., checks cashed, certificate of deposits) and the measures of those out- puts? Third, what are the appropriate ways of measuring the relationship between these inputs and outputs? Measuring Service Productivity ‘The measure of an organization’s productivity, if viewed from an engineering perspec- tive, is similar to the measure of a system’s efficiency. It can be stated as a ratio of out- Puts to inputs (e.g, miles per gallon for an automobile. To evaluate the operational efficiency of a branch bank, for example, an account- ing ratio such as cost per teller transaction might be used. A branch with a high ratio in comparison with those of other branches would be considered less efficient, but the higher ratio could result from @ more complex mix of transactions. For example, a branch opening new accounts and selling CDs would require more time per trans- action than another branch engaged only in simple transactions such as accepting deposits and cashing checks. The problem with using simple ratios is that the mix of ‘outputs is not considered explicitly. This same criticism also can be made concerning the mix of inputs. For example, some branches might have automated teller machines in addition to live tellers, and this use of technology could affect the cost per teller transaction, Broad-based measures such as profitability or retum on investment are highly rel- ‘evant as overall performance measures, but they are not sufficient to evaluate the oper- ating efficiency of a service unit. For instance, one could not conclude that a profitable branch bank is necessarily efficient in its use of personnel and other inputs. A higher than-average proportion of revenue-generating transactions could be the explanation rather than the cost-efficient use of resources. The DEA Model Fortunately, a technique has been developed with the ability to compare the efficiency ‘of multiple service units that provide similar services by explicitly considering their use 204. Part Two Designing the Service Berrie ‘of multiple inputs (i.., resources) to produce multiple outputs (ie, services). The tech- nique, which is referred to as data envelopment analysis (DEA), circumvents the need to develop standard costs for each service, because it can incorporate multiple inputs and ‘multiple outputs into both the numerator and the denominator of the efficiency ratio with- out the need for conversion to a common dollar basis. Thus, the DEA measure of effi- ciency explicitly accounts for the mix of inputs and outputs and, consequently, is more comprehensive and reliable than a set of operating ratios or profit measures. DEA is a linear programming model that attempts to maximize a service unit's efficiency, expressed as a ratio of outputs to inputs, by comparing a particular unit's efficiency with the performance of a group of similar service units that are delivering the same service. In the process, some units achieve 100 percent efficiency and are referred to as the relatively efficient units, whereas other units with efficiency ratings of less than. 100 percent are referred to as inefficient units Corporate management thus can use DEA to compare a group of service units to identify relatively inefficient units, measure the magnitude of the inefficiencies, and by comparing the inefficient with the efficient ones, discover ways to reduce those inefficiencies, ‘The DEA linear programming model is formulated according to Chames, Cooper, and Rhodes, and is referred to as the CCR Model. Definition of Variables Let £i, with k = 1,2, ...,K, be the efficiency ratio of unit, where Kis the total number of units being evaluated. Let, with j = 1, 2, ...,M, be a coefficient for output j, where M is the total number of output types considered. The variable w, is a measure of the relative decrease in effi- ciency with each unit reduction of output value. Let v, with = 1,2, ....N,be a coefficient for input i, where Nis the total number of input types considered. The variable v is a measure of the relative increase in efficiency with each unit reduction of input value. Let Oj. be the number of observed units of output j generated by service unit k during one time period. Let Jy be the number of actual units of input i used by service unit k during one time period. Objective Function The objective is to find the set of coefficient u's associated with each output and of v's associated with each input that will give the service unit being evaluated the highest pos- sible efficiency. MO. + On, +o + ty Owe a Wie + Yala += + Wyle max E, where ¢ isthe index of the unit being evaluated. This function is subject to the constraint that when the same set of input and output coefficients (x's and ys) is applied to all other service units being compared, no service unit will exceed 100 percent efficiency ora ratio of 1.0, Constraints 40 + 20n ++ wOm 1 Malia + Vadag Fo + Vln K @ where all coefficient values are positive and nonzero, To solve this fractional linear programming model using standard linear program- ming software requires a reformulation, Note that both the objective function and all Mm Oy + W202 Example 8.1 Burger Palace TABLE 8.6 Summary of Outputs and Inputs for Burger Palace Chapter 8 Process Improvement 205 ‘constraints are ratios rather than linear functions. The objective function in equation (1) is restated as a linear function by arbitrarily scaling the inputs for the unit under evalua tion to a sum of 1.0 max Ey = Oye + 0x9 + + Uy Ore @) subject to the constraint that Vhe + Vale +--+ Wyle = 1 ® For each service unit, the constraints in equation (2) are similarly reformulated: tot uO — Wile + Vila tot yl) S00 k= (6) where = Las M yw =O §=12...N Sample Size A question of sample size often is raised concerning the number of service units that are required compared with the number of input and output variables selected in the analysis. ‘The following relationship relating the number of service units K used in the analysis and the number of input N and output M types being considered is based on empirical find- ings and the experience of DEA practitioners: K = 2N+M) © ‘An innovative dtive-in-only burger chain has established six units in several different cities. Each unit is located in a strip shopping center parking lot. Only a standard meal consisting of ‘a burger, fries, and a drink is available, Management has decided to use DEA to improve pro- ductivity by identifying which units are using their resources most efficiently and then sharing their experience and knowledge with the less efficent locations. Table 8.6 summarizes data for two inputs: labor-hours and material dollars consumed during atypical lunch hour period to generate an output of 100 meals sold. Normally, output will vary among the service units, bout in this example, we have made the outputs equal to allow for a graphical presentation of the units’ productivity. As Figure 8.19 shows, service units 5), 53, and Ss have been joined to form an effcient-production frontier of alternative methods of using labor hours and mate- Fial resources to generate 100 meals. As can be seen, these efficient units have defined an ‘envelope that contains all the inefficient units—thus the reason for calling the process “data ‘envelopment analysis.” Service Unit Meals Sold Labor-Hours. Material Dollars 1 100 2 200 2 100 4 150 3 100 4 100 4 100 6 100 5 100 8 20 6 100 10 ° 206 Part Two Designing the Service Eerie FIGURE 8.19 Productivity Frontier of, ‘Burger Palace For this simple example, we can identily efficient units by inspection and see the excess inputs being used by ineficient unis (e.g, 5, would be as efficient as 5, if it used $50 less in materials). To gain an understanding of DEA, however, we will proceed to formulate the linear programming problems for each unit, then solve each of them to determine efficiency ratings land other information. ‘We begin by illustrating the LP formulation forthe first service uni, Sy, using equations (3), ),and 6) max E(S,) = 4,100 subject to 4100 — 42 — ¥,200 = 0 4100-4 — »150=0 4100 — 4 — ¥3100 50 100 ~ 46 — y,100 <0 4100 — 48 — v,80=0 4100 ~ 10 - y,50 <0 y2 + ¥,200=1 ts Yin V2 =O Similar linear programming problems are formulated (or, better yet, the 5, linear program- ‘ming problem is edited) and solved for the other service units by substituting the appropriate ‘output function for the objective function and substituting the appropriate input function for the last constraint. Constraints 1 through 6, which restrict all units to no more than 100 per- cent efficiency, remain the same in all problems. ‘This set of six near programming problems was solved with Excel Solver 7.0 in fewer than five minutes by editing the data file between each run. Because the output is 100 meals for all Units, only the last constraint must be edited by substituting the appropriate labor and mate- rial input values from Table 8.6 for the unit being evaluated. “The data file for unit 1 of Burger Palace using a linear programming Excel add-in is shown in Figure 8.20. The linear programming results for each unit are shown in Table 8.7 and sum- marized in Table 8.8. In Table 8.7, we find that DEA has identified the same units shown as being efficient in Figure 8.18. Units 52, Sy, and 5; all ae inefficient in varying degrees. Also shown in Table 8.7 and associated with each inefficient unit is an efficiency reference set. Each inefficient unit will havea set of effcient units associated with it that defines its productivity. As Figure 8.18 shows for inefficient unit 5, the efficent units 5; and 5, have been joined with a line defining the ‘efficiency frontier. A dashed line drawn from the origin to inefficient unit S, cuts through this Chapter 8 Process Improvement 207 TABLE &.7 LP Solutions for DEA Study of Burger Palace Summarized results for unit 1 Page: 1 Variables eee Variables eee No. Names | Solutions ‘costs No. Names| Solutions | costs 1 ur | #1.0000000 of 6 33 0 0 2 vi | +.16666667 ° 7 sa | +33.333336 ° 3 v2 | +.00333333, of 8 ss | +60.000000 ° 4 SI | +1,0000000] 9 so | +83.333336 ° 5 s2__| +16.666670 o| 10 a7 0 | +100.00000 Maximized objective function = 100 Iterations = 4 Summarized results for unit 2 Page: Variables ee Variables ‘Opportunity No. Names | Solutions costs No. Names | Solutions | costs 1 ui | +85714287 o| 6 33 | +.71428573 2 vi | +14zgszis of 7 sa | +28.571430 ° 3 v2 | 00285714 of ss | +51.428574 ° 4 st 0| +0.28571430| 9 ss | +71.428574 ° 5 s2__| +14.285717 of 10 AZ o| +85.714287 Maximized objective function = 85.71429 Iterations = 4 Summarized results for unit 3 Page: bles eee Variables eer No. Names| Solutions ‘costs Ne. Names| Solutions costs 1 ur | +1,0000000 0 6 33 0 | +1,0000000 2 vi | +.06250000 o 7 sa | +12.500000 ° 3 v2 | +.00750000 ° 8 ss | +10.000001 ° 4 SI +62,500000 ° 9 s6 ° ° 5 s2__| +37.500008, 0 10 AZ 0 | +100.00000 Maximized objective function = 100 Iterations = 3 Summarized results for unit 4 Page: ets | Opportunity parities Opportunity No. Names | Solutions costs No. Names | _ Solutions costs 1 ul | +.88888890 ° 6 3 0| +.77777779 2 vi | +.08555556 ° 7 sa | stnaniiz ° 3 v2 | +.00666667 0 a ss | +s.sssaa93 ° 4 st | +55.555553 0 9 56 | +.22222224 5 sz | 433333340 ° 10 ay. 0 | +88.a8888s Maximized objective function = 88.88889 Iterations = 3 Summarized results for unit 5 Page:1 RAE Opportunity variates) Opportunity No. Names| Solutions costs Neo. Names| Solutions costs 1 ur | +.90909088 ° 6 3 0| +.45454547 2 vi | +.05681818 ° 7 sa | +11.363637 ° 3 v2 | +.00681818 ° 8 ss_| +9,0909100 ° 4 si | 456.1810 ° 9 s6 | +.54545450 5 s2__ | +34.090916 o 10 a7 0 | +90.909088 Maximized objective function = 90.90909 Iterations = 4 (continued) 208 Part Two Designing the Service Berrie TABLE 8.7 (concluded) Summarized results for unit 6 Page:1 Variables Variables Opportunity Opportunity Names _| Solutions ‘costs No. Names _| Solutions costs ul vi v2 31 2 +7,0000000 0 6 33 0 ° ++,06250000 sa | +12.500000 ° +.00750000 ss | +10.000001 ° +62.500000 9 56 | +1,0000000 437.5008, 10 AZ | +100.00000 Maximized objective function erations FIGURE 8.20 Excel Data le for DEA Analysis of Burger Palace Unit 1 frontier and, thus, defines unit Sy as inefficient. In Table 8.8, the value in parentheses that is associated with each member of the efficiency reference set (ie,, 7778 for 5, and .2222 for 59 represents the relative weight assigned to that efficient unit in calculating the efficiency rat- ing for 5. These relative weights are the shadow prices that are associated with the respective

You might also like